import plotly.offline as py
py.init_notebook_mode(connected=True)
import plotly.graph_objs as go
import plotly.tools as tls
import warnings
# from plotly.tools import FigureFactory as FF 
warnings.filterwarnings('ignore')
import pandas as pd
import numpy as np

from kaggle.competitions import twosigmanews
# You can only call make_env() once, so don't lose it!
env = twosigmanews.make_env()
print('Done!')

(market_train_df, news_train_df) = env.get_training_data()

import pandas as pd
import matplotlib.pyplot as plt
plt.style.use("fivethirtyeight")
%matplotlib inline
import seaborn as sns
import numpy as np
import plotly.figure_factory as ff


######### Function
def mis_value_graph(data):
#     data.isnull().sum().plot(kind="bar", figsize = (20,10), fontsize = 20)
#     plt.xlabel("Columns", fontsize = 20)
#     plt.ylabel("Value Count", fontsize = 20)
#     plt.title("Total Missing Value By Column", fontsize = 20)
#     for i in range(len(data)):
#          colors.append(generate_color())
            
    data = [
    go.Bar(
        x = data.columns,
        y = data.isnull().sum(),
        name = 'Unknown Assets',
        textfont=dict(size=20),
        marker=dict(
#         color= colors,
        line=dict(
            color='#000000',
            width=2,
        ), opacity = 0.45
    )
    ),
    ]
    layout= go.Layout(
        title= '"Total Missing Value By Column"',
        xaxis= dict(title='Columns', ticklen=5, zeroline=False, gridwidth=2),
        yaxis=dict(title='Value Count', ticklen=5, gridwidth=2),
        showlegend=True
    )
    fig= go.Figure(data=data, layout=layout)
    py.iplot(fig, filename='skin')
    

def mis_impute(data):
    for i in data.columns:
        if data[i].dtype == "object":
            data[i] = data[i].fillna("other")
        elif (data[i].dtype == "int64" or data[i].dtype == "float64"):
            data[i] = data[i].fillna(data[i].mean())
        else:
            pass
    return data


import random

def generate_color():
    color = '#{:02x}{:02x}{:02x}'.format(*map(lambda x: random.randint(0, 255), range(3)))
    return color

mis_value_graph(market_train_df)
market_train_df = mis_impute(market_train_df)
market_train_df.isna().sum().to_frame()

# https://www.kaggle.com/pestipeti/simple-eda-two-sigma

best_asset_volume = market_train_df.groupby("assetCode")["close"].count().to_frame().sort_values(by=['close'],ascending= False)
best_asset_volume = best_asset_volume.sort_values(by=['close'])
largest_by_volume = list(best_asset_volume.nlargest(10, ['close']).index)
# largest_by_volume

for i in largest_by_volume:
    asset1_df = market_train_df[(market_train_df['assetCode'] == i) & (market_train_df['time'] > '2015-01-01') & (market_train_df['time'] < '2017-01-01')]
    # Create a trace
    trace1 = go.Scatter(
        x = asset1_df['time'].dt.strftime(date_format='%Y-%m-%d').values,
        y = asset1_df['close'].values,
        line = dict(color = generate_color()),opacity = 0.8
    )

    layout = dict(title = "Closing prices of {}".format(i),
                  xaxis = dict(title = 'Month'),
                  yaxis = dict(title = 'Price (USD)'),
                  )

    data = [trace1]
    py.iplot(dict(data=data, layout=layout), filename='basic-line')

for i in largest_by_volume:

    asset1_df['high'] = asset1_df['open']
    asset1_df['low'] = asset1_df['close']

    for ind, row in asset1_df.iterrows():
        if row['close'] > row['open']:
            
            asset1_df.loc[ind, 'high'] = row['close']
            asset1_df.loc[ind, 'low'] = row['open']

    trace1 = go.Candlestick(
        x = asset1_df['time'].dt.strftime(date_format='%Y-%m-%d').values,
        open = asset1_df['open'].values,
        low = asset1_df['low'].values,
        high = asset1_df['high'].values,
        close = asset1_df['close'].values,
        increasing=dict(line=dict(color= generate_color())),
        decreasing=dict(line=dict(color= generate_color())))

    layout = dict(title = "Candlestick chart for {}".format(i),
                  xaxis = dict(
                      title = 'Month',
                      rangeslider = dict(visible = False)
                  ),
                  yaxis = dict(title = 'Price (USD)')
                 )
    data = [trace1]

    py.iplot(dict(data=data, layout=layout), filename='basic-line')